Author: Thomas Logan
Date: 04:02:05 08/25/05
Go up one level in this thread
On August 25, 2005 at 03:23:26, Volker Böhm wrote: >Hi, > >please don´t think that the speedup is 3.52 only becase the nps are getting up >by a factor of 3.52. In parallel search many "unnecessary" nodes are searched. >The amount of unnecessary nodes is dependant of the quality of the parallel >algorithm. > >The speedup can only be calculated by looking at the time a program takes to >reach a certain search depth in different position. To test only one position >will not tell you anything. > >Greetings Volker Hi Volker Yes I know that. I believe I asked for speedup numbers in another post Would you have any ideas ? Thanks Tom
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.